© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95260
    Prev
    Next
    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasAnnotation
    -0.49
     المعيارى
    -0.49
    WriteBarrier
    -0.47
     conmigo
    -0.45
    bcryptjs
    -0.45
    ConstraintMaker
    -0.45
    Kariera
    -0.44
     समीक्षक
    -0.44
     الاطلاع
    -0.42
    íslu
    -0.42
    POSITIVE LOGITS
     silly
    0.69
     strange
    0.65
     stupid
    0.64
     daft
    0.64
     weird
    0.63
     resourceCulture
    0.63
    strange
    0.62
     unpredictable
    0.60
     strangest
    0.60
    unusual
    0.59
    Activations Density 0.002%

    No Known Activations